BibTeX:

@article{IJIRSTV3I7050,
     title={Image Retrieval with Ambiguity Resolution using Enhanced Graph based Ranking Model},
     author={Raviraj S. Patkar and S. Pratap Singh},
     journal={International Journal for Innovative Research in Science & Technology},
     volume={3},
     number={7},
     pages={97--101},
     year={},
     url={http://www.ijirst.org/articles/IJIRSTV3I7050.pdf},
     publisher={IJIRST (International Journal for Innovative Research in Science & Technology)},
}

Image ranking is being used by commercial search engine giants to improve the precision of images searched. Traditional image retrieval systems used are based on keyword search. In such query based systems information from the image is not utilized. Manifold Ranking (MR) technique has been successfully applied for content based image retrieval. In this paper an attempt has been made to enhance the novel graph based Efficient Manifold Ranking (EMR) approach to solve ambiguity issue. The main objective is to annotate the images with some manually defined concepts using visual and context based features for learning a latent space. By feeding the latent vectors into existing classification models, it can be applied to multimedia annotation which is one of the most important problems in multimedia retrieval. This paper also aims to show a more sophisticated algorithm to directly incorporate the discriminate information in training.

Manifold Ranking (MR), Efficient Manifold Ranking (EMR)